Skip to content
OpenAI

GPT Oss Safeguard 20b

groq/openai/gpt-oss-safeguard-20b

GPT Oss Safeguard 20b is a reasoning model by OpenAI with function calling, web search, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 131K token context window with up to 66K tokens of output. Priced at $0.075 per million input tokens and $0.3 per million output tokens, it is one of the most cost-efficient options in its class. Access GPT Oss Safeguard 20b through Inworld LLM Inference with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

Input
$0.075
Output
$0.30
Cache read
$0.0375
Context
131.1K
Max output
65.5K
Text→Text
Function CallingWeb SearchReasoningStructured output
Run on your server. Set INWORLD_API_KEY to your API key. Python requires pip install openai; JavaScript requires Node.js 18+; save it as example.mjs.
curl --fail-with-body https://api.inworld.ai/v1/chat/completions \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "groq/openai/gpt-oss-safeguard-20b",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'
Model GPT Oss Safeguard 20bOpenAI SDK compatible

Pricing and providers

Access GPT Oss Safeguard 20b through Inworld LLM Inference or speech to speech via Groq. By using the providers below you agree to their terms, listed under each provider's name in the Legal section.

Modalities
GroqThis pagegroq/openai/gpt-oss-safeguard-20b
$0.075$0.30$0.0375—131.1K65.5K
Text→Text
Prices in USD per 1M tokens.

Start building with GPT Oss Safeguard 20b

Access GPT Oss Safeguard 20b and every other model through LLM Inference or speech to speech. Create a free account and start in minutes.